comfy-api-liberation
Use your own API keys with ComfyUI. No account required.
Browse the latest quality-filtered tools added to YunoDB from verified public project data.
22794 tools
Use your own API keys with ComfyUI. No account required.
Supercharge your applications using Cloudflare Workers and Gemini within minutes (and for free, up to hundreds of requests per day) ☁️✨
"World Models in a Closed-Loop World" (ICLR'26 Oral)
A collection of AWS Korea Startup SA team materials for hands-on labs.
Training and inference code for ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design [ICLR 2025 oral]
Rank images using TrueSkill by comparing them against each other in the browser. 🖼📊
[CCS'24] SafeGen: Mitigating Unsafe Content Generation in Text-to-Image Models
📚 Process PDFs, Word documents and more with spaCy
Domain-Aware Neurosymbolic Agent (Dana), an agent-native programming language
Multi-model DAG-driven parallel AI film generation — parallel speedup scales with scene independence; Generate film scenes simultaneously instead of one by one;
The Dream Machine — a config-driven engine for nightly, cloud-scheduled, evidence-gated repository evolution. Composes @metaharness/flywheel, darwin, and redblu
Papers & Works for large languange models (OpenAI GPT-4, Meta Llama, etc.).
[NeurIPS 2025 Spotlight] A Unified Tokenizer for Visual Generation and Understanding
[ICLR 2025] xFinder: Large Language Models as Automated Evaluators for Reliable Evaluation
[NeurIPS 2024] Knowledge Circuits in Pretrained Transformers
This is the repo for the survey of LLM4IR.
MiniMax-M2, a model built for Max coding & agentic workflows.
GPU-optimized framework for training diffusion language models at any scale. The backend of Quokka, Super Data Learners, and OpenMoE 2 training.
SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution [ICSE 2026]
[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image G
Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
SoTA production-ready AI retrieval system. Agentic Retrieval-Augmented Generation (RAG) with a RESTful API.
Survey of Small Language Models from Penn State, ...